© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 20654
    Prev
    Next
    INDEX
    Explanations

    linguistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    1.26
    ade
    1.22
    h
    1.20
    ala
    1.16
    anns
    1.10
    ية
    1.09
     and
    1.07
    ali
    1.06
    arn
    1.05
    الية
    1.03
    POSITIVE LOGITS
    ও
    1.36
    า
    1.27
     в
    1.21
     a
    1.18
     in
    1.18
     حتی
    1.12
    ในช่วง
    1.12
     be
    1.11
    OR
    1.04
    も含
    1.02
    Activations Density 0.003%

    No Known Activations